In this work, we propose a similarity-aware CAC framework that jointly learns representation and similarity metric.
Remote photoplethysmography (rPPG) based physiological measurement has great application values in health monitoring, emotion analysis, etc.
Bootstrapping provides a flexible and effective approach for assessing the quality of batch reinforcement learning, yet its theoretical property is less understood.
By looking at existing upsampling operators from a unified mathematical perspective, we generalize them into a second-order form and introduce Affinity-Aware Upsampling (A2U) where upsampling kernels are generated using a light-weight lowrank bilinear model and are conditioned on second-order features.
Heterogeneous ice nucleation is one of the most common and important process in the physical environment.
Inspired by scale weighing, we propose a novel 'counting scale' termed LibraNet where the count value is analogized by weight.
This paper is concerned with solving combinatorial optimization problems, in particular, the capacitated vehicle routing problems (CVRP).
Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i. e., the number of population can vary in [0, inf) in theory.
A dense region can always be divided until sub-region counts are within the previously observed closed set.
Ranked #4 on Crowd Counting on ShanghaiTech A
By viewing the indices as a function of the feature map, we introduce the concept of "learning to index", and present a novel index-guided encoder-decoder framework where indices are self-learned adaptively from data and are used to guide the downsampling and upsampling stages, without extra training supervision.
Ranked #2 on Scene Segmentation on SUN-RGBD
We show that existing upsampling operators can be unified with the notion of the index function.
However, robust depth prediction suffers from two challenging problems: a) How to extract more discriminative features for different scenes (compared to a single scene)?
We study the hypothesis testing problem of inferring the existence of combinatorial structures in undirected graphical models.
In this paper we study the problem of monocular relative depth perception in the wild.
Domain adaption (DA) allows machine learning methods trained on data sampled from one distribution to be applied to data sampled from another.
To our knowledge, this is the first time that a plant-related counting problem is considered using computer vision technologies under unconstrained field-based environment.